An explanation for one of the most broadly used and important algorithms in Machine Learning

Photo credit

You’re stuck on a mountain, surrounded by a dense fog. You didn’t sign up for this. You simply wanted to solve for the optimal values of a regression, but it was too computationally inefficient and expensive because you had too many features. So, here you magically are. You can get down the mountain and out of the fog the fastest by going down the steepest slope. You do this. You find a Saint Bernard with a flagon of “water” around her neck and you’re saved.

This is the idea behind Gradient Descent, an iterative process (steps) that takes us to…


I’m not sure if you’ve noticed, but every movie (fine, a simple grand majority) is one of these: a spinoff, sequel, part of a universe, a remake. It’s not just anecdotal evidence, it’s empirical. Of the top 25 grossing movies domestically, according to Box Office Mojo, 21 of them fall into one of those categories.

But, seriously, why deviate from this new normal? It makes money… a lot. If you have a piece of intellectual property (IP) and it’s made money, why not ride the wave? …

Ripton Rosen

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store